Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 949 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.4593. Min Act: -0.1700
Data Index: 6683015 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.2718. Min Act: -0.1700
Data Index: 1317652 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.1781. Min Act: -0.1700
Data Index: 2346621 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.1468. Min Act: -0.1700
Data Index: 4765835 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.1468. Min Act: -0.1700
Data Index: 4218125 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.0843. Min Act: -0.1700
Data Index: 3180482 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.0531. Min Act: -0.1700
Data Index: 1252679 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.0531. Min Act: -0.1700
Data Index: 3682731 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.0531. Min Act: -0.1700
Data Index: 6145421 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.0218. Min Act: -0.1700
Data Index: 2257795 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4593. Min Range: -5.4593
Max Act: 4.9906. Min Act: -0.1700
Data Index: 6309897 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4593. Min Range: -5.4593
Max Act: 4.9906. Min Act: -0.1700
Data Index: 2238909 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4593. Min Range: -5.4593
Max Act: 4.9593. Min Act: -0.1700
Data Index: 1552127 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4593. Min Range: -5.4593
Max Act: 4.9593. Min Act: -0.1700
Data Index: 1223630 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4593. Min Range: -5.4593
Max Act: 4.9593. Min Act: -0.1700
Data Index: 8618110 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4593. Min Range: -5.4593
Max Act: 4.9593. Min Act: -0.1700
Data Index: 8785576 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4593. Min Range: -5.4593
Max Act: 4.9593. Min Act: -0.1700
Data Index: 4206729 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4593. Min Range: -5.4593
Max Act: 4.9281. Min Act: -0.1700
Data Index: 6937748 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4593. Min Range: -5.4593
Max Act: 4.9281. Min Act: -0.1700
Data Index: 5702839 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4593. Min Range: -5.4593
Max Act: 4.9281. Min Act: -0.1700
Data Index: 7600090 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19